{"model": {"slug": "claude-3-5-sonnet-20240620", "name": "Claude 3.5 Sonnet (2024-06-20)", "vendor": "Anthropic", "model_family": "claude-3-5-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.5 Sonnet (2024-06-20) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 77.4, "input_price_per_million": null, "output_price_per_million": null}, "scores": [{"success_rate": 77.4, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Aider edit leaderboard", "source": "aider_leaderboard", "source_url": "https://aider.chat/docs/leaderboards/", "observed_at": "2024-07-04T00:00:00+00:00", "harness": {"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "claude-3-5-sonnet-20240620", "name": "Claude 3.5 Sonnet (2024-06-20)", "vendor": "Anthropic"}, "benchmark": {"slug": "aider-edit", "name": "Aider Edit"}}, {"success_rate": 64.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Aider refactor leaderboard", "source": "aider_leaderboard", "source_url": "https://aider.chat/docs/leaderboards/", "observed_at": "2024-07-01T00:00:00+00:00", "harness": {"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "claude-3-5-sonnet-20240620", "name": "Claude 3.5 Sonnet (2024-06-20)", "vendor": "Anthropic"}, "benchmark": {"slug": "aider-refactor", "name": "Aider Refactor"}}, {"success_rate": 7.56, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "MLE-bench All split any_medal_percentage", "source": "mle_bench_site", "source_url": "https://github.com/openai/mle-bench", "observed_at": "2024-10-08T00:00:00+00:00", "harness": {"slug": "aide", "name": "AIDE", "vendor": "Wecoai", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "claude-3-5-sonnet-20240620", "name": "Claude 3.5 Sonnet (2024-06-20)", "vendor": "Anthropic"}, "benchmark": {"slug": "mle-bench", "name": "MLE-bench"}}], "harnesses": [{"slug": "aide", "name": "AIDE", "vendor": "Wecoai", "repo_url": "https://github.com/wecoai/aideml", "openrouter_icon_url": null}, {"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": "https://github.com/Aider-AI/aider", "openrouter_icon_url": "https://aider.chat/favicon.ico"}]}